News about autonomous vehicles is coming thick and fast. Yesterday we learned about truck platoons that can drive themselves across Europe and today I bring you a fleet of self-driving taxis is launching in Singapore from a company called nuTonomy.
According to a post from MIT (where nuTonomy started out three years ago) the company passed its first driving tests and is in the process of getting approval for road testing. It makes sense that driverless car technology would make its first appearance in the tiny city state, roads are notoriously congested and the government has tried everything from high taxation to even/odd driving days to keep the downtown streets free of traffic.
But to really make things work, you need to have sophisticated algorithms manage where to place the cars and which routes to drive.
One such innovation is advanced fleet management, derived from Frazzoli’s previous work writing algorithms to coordinate swarms of drones for the U.S. military. Using similar concepts, Frazzoli, Iagnemma, and nuTonomy’s engineers designed algorithms to allow the minimal number of cars to cart people around a city, alleviating traffic congestion and reducing emissions. In a 2014 paper published in Road Vehicle Automation, Frazzoli and colleagues estimated that 300,000 driverless taxis, in theory, could do the work of the 780,000 privately owned cars currently operating today in Singapore, while keeping waiting times below 15 minutes.
In addition to the algorithms, nuTonomy has built in rules which allow the cars to override traffic laws when prudent. We all know that when a truck is flashing its blinkers and double-parked that we can make an exception, when oncoming traffic is clear, to cross over a double-line and get around the truck. Teaching this to a self-driving car is more nuanced and difficult.
“Robot Taxis” are being planned for 2020 Tokyo Olympics. I’m sure they will be watching the field tests in Singapore closely.